Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    add to taste

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Umbrella
    0.46
     citt
    0.45
     দিন
    0.44
    の発
    0.42
     Publicity
    0.42
     Natasha
    0.41
     Khar
    0.40
     Goddess
    0.40
     Cupid
    0.40
     Currency
    0.40
    POSITIVE LOGITS
     añade
    0.52
    加入
    0.47
     añadi
    0.47
    我们
    0.46
     añadir
    0.46
     hacemos
    0.45
     добавля
    0.45
    dsb
    0.44
    bdb
    0.44
     تضيف
    0.44
    Act Density 0.002%

    No Known Activations